Skip to main content Skip to secondary navigation

Machine learning about ice

Main content start
Mickey MacKie
(Photo courtesy of Mickey MacKie)

Mickey MacKie

PhD '21

June 7, 2021

“While I was an undergrad student at Harvard, I was fascinated with learning about Precambrian Snowball Earth geology and glacial geology,” said Mickey MacKie, PhD ’21. “I feel so lucky that I’ve been able to making a career out of something that I love – and which also has implications for contemporary issues like sea-level rise.”

While at Stanford, MacKie’s work focused on using ice-penetrating radar and geostatistical simulations to understand ice sheet behavior. Alongside other members of the Stanford Radio Glaciology Lab led by geophysics professor Dustin Schroeder, MacKie has trekked to Greenland and Svalbard, Norway, to characterize conditions beneath ice sheets, including the topography, hydrology, and geology.

“The fieldwork that I’ve done in Greenland and Svalbard has been so important in helping me to understand glaciers,” MacKie said. “These experiences enable me to contextualize and better interpret ice sheet datasets.”

Following graduation, Mackie will begin as an assistant professor in the geological sciences department at the University of Florida. “I’m looking forward to opportunities to continue work that I began while at Stanford – like developing machine learning approaches for studying the cryosphere that will help improve the accuracy and rigor of sea-level rise projections – as well as new opportunities to teach artificial intelligence and machine learning to ensure every student graduates with those skill sets,” says MacKie.

She is especially excited to join a growing community of machine learning experts in the next stage of her career. “The University of Florida has the most powerful supercomputer in academia and is in the process of hiring over 100 new faculty who specialize in different applications of machine learning,” she said. “I’m looking forward to using those computational resources, collaborating with the machine learning community there, and working with incredible students to make new discoveries.”